Commit
•
cd9a69a
1
Parent(s):
be88bee
Update README.md
Browse files
README.md
CHANGED
|
@@ -32,9 +32,28 @@ You can use this model directly with a pipeline for masked language modeling:
|
|
| 32 |
```python
|
| 33 |
>>> from transformers import pipeline
|
| 34 |
>>> unmasker = pipeline('fill-mask', model='facebook/xlm-roberta-xl')
|
| 35 |
-
>>> unmasker("
|
| 36 |
-
|
| 37 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
```
|
| 39 |
|
| 40 |
Here is how to use this model to get the features of a given text in PyTorch:
|
|
|
|
| 32 |
```python
|
| 33 |
>>> from transformers import pipeline
|
| 34 |
>>> unmasker = pipeline('fill-mask', model='facebook/xlm-roberta-xl')
|
| 35 |
+
>>> unmasker("Europe is a <mask> continent.")
|
| 36 |
+
|
| 37 |
+
[{'score': 0.08562745153903961,
|
| 38 |
+
'token': 38043,
|
| 39 |
+
'token_str': 'living',
|
| 40 |
+
'sequence': 'Europe is a living continent.'},
|
| 41 |
+
{'score': 0.0799778401851654,
|
| 42 |
+
'token': 103494,
|
| 43 |
+
'token_str': 'dead',
|
| 44 |
+
'sequence': 'Europe is a dead continent.'},
|
| 45 |
+
{'score': 0.046154674142599106,
|
| 46 |
+
'token': 72856,
|
| 47 |
+
'token_str': 'lost',
|
| 48 |
+
'sequence': 'Europe is a lost continent.'},
|
| 49 |
+
{'score': 0.04358183592557907,
|
| 50 |
+
'token': 19336,
|
| 51 |
+
'token_str': 'small',
|
| 52 |
+
'sequence': 'Europe is a small continent.'},
|
| 53 |
+
{'score': 0.040570393204689026,
|
| 54 |
+
'token': 34923,
|
| 55 |
+
'token_str': 'beautiful',
|
| 56 |
+
'sequence': 'Europe is a beautiful continent.'}]
|
| 57 |
```
|
| 58 |
|
| 59 |
Here is how to use this model to get the features of a given text in PyTorch:
|